发表机构
University of Maryland（马里兰大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对土耳其语-英语代码混合文本，构建了TurEngMix语料库与基准，评估显示形态整合标记的错误率高，并发布资源以促进研究。
AI 中文摘要
自然语言处理系统在代码混合文本上表现不佳，尤其是在低资源语言对上。土耳其语-英语构成了进一步的挑战：它允许英语词干与土耳其语后缀结合，形成单个混合语言标记。我们引入了TurEngMix，一个包含5.5K条嘈杂的、自然发生的社交媒体帖子（486,974个标记）的语料库，这些帖子富含土耳其语-英语代码混合。从该语料库中，我们构建了一个新的土耳其语-英语基准，用于代码混合语言识别（LID）和命名实体识别（NER），包含15K个专家标注的标记。通过评估解码器LLM和微调编码器基线，我们发现单语土耳其语和英语标记被可靠地标注，但所有模型在混合语言标记上的LID和NER错误率都很高。对于形态整合的标记，GPT-4o和Qwen的NER错误率分别高出5.2倍和6.3倍。这突显了形态整合仍然是一个挑战。我们发布了语料库、标注和代码，以支持未来关于土耳其语-英语代码混合的计算和社会语言学研究。
英文摘要
Natural language processing systems underperform on code-mixed text, particularly for low-resource language pairs. Turkish-English poses a further challenge: it lets English stems combine with Turkish suffixes to form single mixed-language tokens. We introduce TurEngMix, a corpus of 5.5K noisy, naturally occurring social media posts (486,974 tokens) rich in Turkish-English code-mixing. From this corpus, we construct a new Turkish-English benchmark for code-mixed language identification (LID) and named entity recognition (NER), comprising 15K expert-annotated tokens. Evaluating both decoder LLM and fine-tuned encoder baselines, we find that monolingual Turkish and English tokens are labeled reliably, but all models have high error rates on mixed-language tokens for both LID and NER. For morphologically integrated tokens, NER error rates were 5.2x and 6.3x higher for GPT-4o and Qwen, respectively. This highlights how morphological integration remains a challenge. We release the corpus, annotations, and code to support future computational and sociolinguistic research on Turkish-English code-mixing.
CommentsAccepted to W-NUT 2026 (11th Workshop on Natural User-generated Text), co-located with EMNLP 2026. 15 pages, 4 figures, 12 tables
